# Micro Neural Policies for Safe Real-Time Robotic Control

arXiv: https://arxiv.org/abs/2610.08541 · HTML: https://mlsanity.com/paper/2610.08541/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 9 of 9)

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [Residual Policy Learning](https://mlsanity.com/paper/1812.06298/) (2018)
- [What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study](https://mlsanity.com/paper/2006.05990/) (2020)
- [MLPerf Tiny Benchmark](https://mlsanity.com/paper/2106.07597/) (2021)
- [A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Drones](https://mlsanity.com/paper/1805.01831/) (2018)
- [SMC-ES: Automated synthesis of formally verified control policies](https://mlsanity.com/paper/2607.15003/) (2026)
- [Safe and Robust Neural Policy Learning with Statistical Verification for Sim-to-Real Deployment in Robotics](https://mlsanity.com/paper/2608.06481/) (2026)

## Abstract (arXiv)

In this paper, we investigate the synthesis of Micro Neural Policies (MNP) to enable safe and robust real-time robotic control on computationally constrained embedded devices. We demonstrate that integrating Evolution Strategy (ES) and Statistical Model Checking (SMC)-based verification for policy search can drastically reduce neural network size without compromising safety and robustness. We conduct a large-scale training and evaluation of MNP on Cartpole and Quadrotor control tasks, varying control frequencies and network architectures. After validating these policies in simulation, we evaluate their deployability through zero-shot transfer to physical systems. Our experiments show that MNP can successfully achieve safe sim-to-real transfer without sacrificing control performance. We then show that the policies' memory footprint, ranging from 0.5 to 7.5 kB, allows deployment on microcontrollers, where they achieve real-time inference latency with under 25 ns of jitter while leaving the chip idle for over 97% of the time for additional workloads. This makes them a highly practical solution for severely resource-constrained robotic systems.